update to code agent

app.py

@@ -729,14 +729,14 @@ with gr.Blocks(title="🤖 French Public Data Analysis Agent", theme=gr.themes.S
     followup_section_header = gr.HTML("""
     <div style="text-align: center; margin: 2rem 0;">
         <h2 style="color: #374151; margin-bottom: 0.5rem;">🤖 Follow-up Analysis</h2>
-        <p style="color: #6b7280; margin: 0;">Ask questions about the generated report and dataset</p>
+        <p style="color: #6b7280; margin: 0;">Ask about report findings, request data analysis, or get contextual information</p>
     </div>
     """, visible=False)
     
     with gr.Row(visible=False) as followup_input_row:
         followup_input = gr.Textbox(
             label="Follow-up Question",
-            placeholder="e.g., Show me correlation between two columns, Create a chart for specific regions, What are the trends over time?",
+            placeholder="e.g., What are the main findings?, Show me correlation between columns, What is road safety policy in France?",
             scale=4
         )
         followup_button = gr.Button(
@@ -772,12 +772,12 @@ with gr.Blocks(title="🤖 French Public Data Analysis Agent", theme=gr.themes.S
     
     with gr.Row(visible=False) as followup_examples_row:
         followup_examples = [
-            ("📊 Correlation Analysis", "Show me the correlation between two numerical columns with a scatter plot"),
-            ("📈 Statistical Summary", "Create a comprehensive statistical summary with visualization for a specific column"),
-            ("🎯 Filter & Analyze", "Filter the data by specific criteria and create a visualization"),
-            ("📋 Dataset Overview", "Give me a detailed summary of the dataset structure and contents"),
-            ("📉 Trend Analysis", "Create a line chart showing trends over time for specific data"),
-            ("🔍 Custom Visualization", "Create a custom bar/pie/histogram chart for specific columns"),
+            ("📋 Report Summary", "What were the main findings from the analysis?"),
+            ("🌐 Context Info", "What is the policy context for this data in France?"),
+            ("📊 Create Chart", "Show me the correlation between two numerical columns with a scatter plot"),
+            ("📈 Data Statistics", "Give me statistical summary for a specific column"),
+            ("🎯 Filter Data", "Filter the data by specific criteria and show results"),
+            ("🔍 General Question", "Tell me more about this topic and its importance"),
         ]
         
         for emoji_text, query_text in followup_examples:

followup_agent.py

@@ -57,37 +57,49 @@ def generate_followup_prompt(user_question, report_context=None):
 
 USER'S FOLLOW-UP QUESTION: "{user_question}"
 
+IMPORTANT: Analyze the user's question carefully to determine what type of response is needed. 
+
+QUESTION ANALYSIS:
+- **General Information/Web Search**: If the question asks for general information, definitions, or requires web search (e.g., "What is X?", "Tell me about Y", "How does Z work?"), use web search tools and provide a text answer. DO NOT load datasets or create visualizations.
+
+- **Dataset Questions**: If the question is specifically about the dataset, data analysis, statistics, or requests visualizations (e.g., "Show me correlation", "Create a chart", "What's the distribution of X?", "Filter by Y"), then use dataset tools.
+
+- **Report Context**: If the question asks about the previous report content or findings, use get_previous_report_content() and provide a text answer.
+
 AVAILABLE TOOLS:
-1. **load_previous_dataset()** - Load the dataset used in the previous analysis
-2. **get_dataset_summary(df)** - Get detailed info about the dataset structure
-3. **get_previous_report_content()** - Get context about the previous report
-4. **create_followup_visualization()** - Create new charts and graphs (bar, line, scatter, histogram, box, pie)
-5. **analyze_column_correlation()** - Analyze relationships between columns with scatter plots
-6. **create_statistical_summary()** - Generate comprehensive stats + visualizations for any column
-7. **filter_and_visualize_data()** - Filter data by criteria and create targeted visualizations
-8. **search_datasets()** - Search for additional datasets if needed
-9. **get_dataset_info()** - Get info about specific datasets
-
-ANALYSIS APPROACH:
-1. First, get context by calling get_previous_report_content()
-2. Load the previous dataset using load_previous_dataset()
-3. Get a summary of the dataset structure with get_dataset_summary()
-4. Based on the user's question, perform the appropriate analysis:
-   - Create new visualizations if they want different charts
-   - Analyze correlations if they ask about relationships
-   - Filter or group data if they want specific subsets
-   - Calculate statistics if they want numerical insights
-5. **ALWAYS create visualizations when relevant** - save to generated_data folder
-6. Provide a comprehensive text answer AND create supporting visualizations
-
-IMPORTANT GUIDELINES:
-- Always start by understanding the previous report context
-- Use the same dataset that was used in the original analysis
-- **CREATE VISUALIZATIONS whenever possible** - charts help answer questions better
-- Provide clear, actionable insights in TEXT format
-- Save all new visualization files to the generated_data folder with descriptive filenames
-- Be concise but thorough in your explanations
-- Combine text analysis with visual evidence
+1. **DuckDuckGoSearchTool** - For general web search and information queries
+2. **get_previous_report_content()** - Get context about the previous report
+3. **load_previous_dataset()** - Load the dataset (ONLY if question needs data analysis)
+4. **get_dataset_summary(df)** - Get dataset structure info
+5. **create_followup_visualization()** - Create charts (ONLY if explicitly requested)
+6. **analyze_column_correlation()** - Analyze column relationships with plots
+7. **create_statistical_summary()** - Generate stats with visualizations
+8. **filter_and_visualize_data()** - Filter data and create targeted visualizations
+9. **search_datasets()** - Search for additional datasets
+10. **get_dataset_info()** - Get info about specific datasets
+
+RESPONSE STRATEGY:
+1. **First, determine the question type:**
+   - Is this a general knowledge/web search question? → Use web search, provide text answer
+   - Is this about the previous report content? → Use get_previous_report_content(), provide text answer
+   - Is this a data analysis question? → Use dataset tools as needed
+   - Does it explicitly ask for a chart/visualization? → Use appropriate visualization tools
+
+2. **For data analysis questions only:**
+   - Load dataset if you need to analyze the actual data
+   - Create visualizations ONLY if the user explicitly asks for them or if the question specifically requires visual analysis (correlations, distributions, trends)
+   - Provide clear text explanations
+
+3. **Be efficient with tool usage:**
+   - Use the minimum number of tools needed to answer the question
+   - Don't create visualizations unless requested or clearly needed
+   - Don't load datasets for general questions
+
+GUIDELINES:
+- Match your response type to the question type
+- Be direct and efficient - don't over-engineer the response
+- Only use data analysis tools when the question is actually about data analysis
+- Provide concise, helpful answers focused on what the user asked
 
 Answer the user's question: "{user_question}"
 """